update description

app.py

@@ -28,7 +28,7 @@ mask_generator = SamAutomaticMaskGenerator(sam)
 
 
 controlnet, controlnet_params = FlaxControlNetModel.from_pretrained(
-    "mfidabel/controlnet-segment-anything", dtype=jnp.float32
+    "SAMControlNet/sd-controlnet-sam-seg", dtype=jnp.float32
 )
 
 pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
@@ -49,13 +49,15 @@ with gr.Blocks() as demo:
     gr.Markdown("# WildSynth: Synthetic Wildlife Data Generation")
     gr.Markdown(
         """
-        We have trained a JAX ControlNet model with
-    To try the demo, upload an image and select object(s) you want to inpaint.
-    Write a prompt & a negative prompt to control the inpainting.
-    Click on the "Submit" button to inpaint the selected object(s).
-    Check "Background" to inpaint the background instead of the selected object(s).
-
-    If the demo is slow, clone the space to your own HF account and run on a GPU.
+        ### About
+        We have trained a JAX ControlNet model for semantic segmentation on Wildlife Animal Images.
+        
+        For the training data creation we used the [Wildlife Animals Images](https://www.kaggle.com/datasets/anshulmehtakaggl/wildlife-animals-images) dataset.
+        We created segmentation masks with the help of [Grounded SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything) where we used the animals names 
+        as input prompts for detection and more accurate segmentation.
+        
+        ### How To Use
+        
     """
     )
     with gr.Row():